kai-webinar
Pass
Audited by Gen Agent Trust Hub on Sep 28, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill invokes local Python scripts (
scripts/quality_gates/four_us_score.pyandscripts/quality_gates/banned_word_check.py) via the command line to perform automated quality checks on generated marketing assets. - [INDIRECT_PROMPT_INJECTION]: The skill has a broad ingestion surface, reading various project files such as
README.md,PROJECT.md, and landing pages to automatically derive product context. If these files contain malicious instructions, they could influence the agent's behavior. - Ingestion points: Phase 0 reads from
CLAUDE.md,README.md,PROJECT.md,package.json, and landing pages. - Boundary markers: The instructions do not specify any delimiters or safety prompts to isolate the ingested data from the agent's core logic.
- Capability inventory: The skill possesses file system read/write capabilities and the ability to execute Python scripts.
- Sanitization: No validation or sanitization of the content from the analyzed files is described.
Audit Metadata